build1 publisher
JetBrains ships a 50/50 weight average of two Qwen checkpoints in Junie Local
The merged 27B finished 37 of 100 internal coding tasks against 34 for the fast checkpoint and 39 for the reasoning one, and it did that while emitting 71% fewer output tokens than the 39, with no post-training in the recipe.
Publishers:blog.jetbrains.com
Reality
- Evidence55
- Adoption30
- Hype gap+18
- Incentives78
- Confidence58